"Remote desktop control and assistance tools" matching MCP servers:

An MCP server that lets AI agents control Android TVs via ADB, including searching and playing content across streaming services, managing power and volume, and sending remote control commands.

Enables Claude Agent SDK agents to safely operate a remote user machine via a WebSocket tunnel, providing six client__* MCP tools with path fencing and phase-switch adjudication.

Enables AI services like Claude and Cursor to remotely control a Mac by executing shell commands, managing files, and running AppleScript for UI automation. Access is secured through OAuth 2.0 authentication and encrypted tunnels to protect remote interactions.

Turns Canvas LMS into a scriptable pipeline and exposes it to AI assistants via MCP for querying courses, grades, assignments, and syncing files using natural language.

Enables an AI agent or script to control Android TV and LG webOS devices over streamable HTTP, including key presses, app launches, power and wake, input switching, sleep timers, toasts, status checks, screenshots, and device scans, with bearer-token authentication and an app denylist.

Enables OAuth-authenticated MCP clients to list registered SwitchBot devices, read their status, and switch plugs on or off via a Cloudflare Workers deployment. Access is limited to an allowlisted set of devices, and turning off a PC plug requires the caller to confirm a clean shutdown first.

Search and pull 620+ React and Tailwind sections into your project over MCP.

Educational tools agent by Birkan Yavuz — an A2A + MCP server for classroom tools, with creator attribution in every result. It offers a catalog of 24 real classroom activities, including math visualizers and reading and sight-word tools.

Vision-capable MCP server for controlling Amazon Fire TV through Home Assistant, providing screenshot-guided observation, remote commands, and app/URI actions via authenticated REST calls.

Comprehensive MCP server providing full programmatic control over the Perplexity API, including agent, sonar, search, embeddings, key management, and cost estimation tools.

Enables LLM coding agents to inspect, control, and verify remote ROS2 robotics applications without a local ROS2 installation, supporting topics, services, actions, parameters, TF transforms, and automated test suites.

Operate the OpenClaw gateway's full management surface from any MCP client — list and trigger crons, inspect sessions, configure agents and channels, manage skills and secrets, pair devices, and more via 134 typed tools.

Provides access to the Reuters Business and Financial News API to retrieve articles, trending news, and market data. It enables searching and filtering financial content by date, author, category, and keywords.

Allows AI assistants to connect to and control Minecraft players on remote servers, enabling navigation, building, mining, inventory management, entity interaction, and chat communication through natural language commands.

Enables access to Usage and Billing APIs for managing accounts, products, meters, plans, and usage reporting. Supports operations like creating products/plans, reporting usage, and retrieving billing information.

An MCP server that lets you execute commands, manage files, run persistent shell sessions, transfer large files, and control background processes on remote machines via a lightweight HTTP agent, useful when SSH/WinRM/SMB are unavailable.

MCP server providing parser-backed validation, parsing, documentation, and editor assistance for AI agents working with _hyperscript.

Enables ChatGPT to access a remote computer or server via an outbound-only agent, providing filesystem inspection, file editing, Git inspection, and optional shell execution through MCP.

Enables AI clients to securely reach and control tools running on your own computers through a relay and outbound device agent.

Enables users to resolve library identifiers and retrieve Context7-compatible documentation through tools that forward requests to the hosted Context7 remote MCP endpoint.

Enables AI coding agents and MCP clients to securely execute shell commands, manage files, and access remote devices or SSH hosts through centralized authentication, routing, and auditing.

Enables MCP clients to securely connect to a paired Windows machine through a self-hosted Cloudflare relay and use its local filesystem and command-execution tools over Streamable HTTP and WebSocket.

Self-hosted Linux server control integration that lets remote MCP clients authenticate through persistent OAuth and invoke file, patch, command, terminal, Git, and image tools. Clients can also subscribe to targeted, signed event notifications for experimental event-driven workflows.

A passive MCP server that exposes a toolbox of executable tools (shell, network, HTTP, AI search, SSH, S3 file operations) to autonomous agents via Streamable HTTP, with strong security features including Docker sandboxing and WAF.

Enables users to deploy a production-grade control plane for agents, providing a spec-compliant MCP server, scoped tool grants, failure-mode detection, and cost governance.

Enables Claude to interact with AMPERA Mission Control to read and write organizational data (initiatives, tasks, risks, decisions, etc.) with role-scoped permissions via the Mission Control REST API.

Enables recall of promoted team and org knowledge from GitHub repositories via Claude.ai, supporting search and status checks.

Enables AI agents to query multi-cloud costs, inventory, waste, and commitments across AWS, GCP, Cloudflare, and OVH through read-only MCP tools.

Enables AI agents to securely read, plan, and sync real trips from the Trek WeChat mini-program via authenticated remote MCP, supporting tools for itinerary management, reservations, and file attachments.

Forwards GitHub tool calls to GitHub's hosted Copilot remote MCP endpoint, enabling repository, branch, file, search, issue, and pull request operations without a local REST client. Exposes a pinned core set of 14 tools authenticated with a personal access token.